Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains

Mahmoud Saeedi Kelishami

cs.CVSep 21, 2026

Directional Total Variation-Regularized Implicit Neural Representations (DTV-INR) for Continuous Super-Resolution in Degraded Imaging Domains

Authors: Mahmoud Saeedi Kelishami

Organizations: Department of Mathematics, Institute of Biosocial and Quantum Science and Technologies, Rasht Branch, Islamic Azad University, Rasht, Iran

Abstract

In this paper, we introduce the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR), an advanced variational paradigm that synergistically integrates coordinate-driven implicit neural networks with an anisotropic, structure-tensor-informed total variation regularizer tailored for resolution-agnostic image super-resolution. Casting the continuous-to-discrete acquisition process into an ill-posed inverse problem framework, our formulation equips a SIREN-architected coordinate network with a dynamic Riemannian metric tensor field D(x). By leveraging its spectral decomposition, the proposed regularizer preferentially directs diffusion parallel to dominant structural contours while penalizing cross-edge dissipation, successfully circumventing the classical staircasing artifacts inherent to scalar total variation schemes. We rigorously prove the well-posedness of this formulation in H^1(Omega) by establishing the existence, uniqueness, and metric stability of the variational minimizer, and realize this via an alternating projected optimization algorithm that decouples network parameter tuning from adaptive tensor field updates. Comprehensive experiments conducted on clinical brain magnetic resonance imaging (MRI) and biomedical transmission electron microscopy confirm substantial quantitative and qualitative improvements, yielding PSNR enhancements reaching +5.05 dB over baseline unregularized INRs and +1.71-2.85 dB over isotropic TV-INR across continuous (non-integer) upsampling factors, alongside remarkable noise robustness up to sigma_eta = 0.10 and monotonic preconditioned convergence behavior.

Figures & tables

Method	Type	$\times 2$	$\times 3$	$\times 4$	$\times 6$	$\times 8$
Bicubic Interpolation	Continuous	31.84 / 0.884	28.52 / 0.812	26.21 / 0.745	23.12 / 0.638	21.20 / 0.542
Discrete TV (CP)	Discrete	33.40 / 0.902	29.80 / 0.835	27.42 / 0.778	24.15 / 0.672	22.08 / 0.579
EDSR	Discrete	35.42 / 0.931	31.80 / 0.875	29.20 / 0.821	25.24 / 0.710 †	22.80 / 0.612 †
LIIF (Continuous SR)	Implicit	36.21 / 0.942	32.74 / 0.891	30.52 / 0.852	27.40 / 0.781	25.12 / 0.715
Vanilla SIREN INR	Implicit	33.95 / 0.910	30.12 / 0.846	27.65 / 0.784	24.38 / 0.680	22.25 / 0.584
Isotropic TV-INR	Implicit	35.80 / 0.935	32.15 / 0.880	30.70 / 0.856	26.85 / 0.765	24.45 / 0.692

Table 1: Quantitative reconstruction performance (PSNR [dB] / SSIM) across varying magnification factors

s

on biomedical microscopic and neuroimaging test suites. Best results are highlighted in bold , and second-best are underlined .

Method	$\sigma_{\eta}{=}0.01$	$\sigma_{\eta}{=}0.03$	$\sigma_{\eta}{=}0.05$	$\sigma_{\eta}{=}0.07$	$\sigma_{\eta}{=}0.10$
Bicubic	27.40/0.781/0.384	24.80/0.695/0.452	22.10/0.584/0.540	20.20/0.490/0.621	17.80/0.385/0.710
LIIF	31.85/0.882/0.220	28.60/0.804/0.295	25.40/0.712/0.385	22.90/0.605/0.480	19.80/0.485/0.602
Vanilla SIREN	30.50/0.865/0.252	27.00/0.762/0.334	23.40/0.640/0.442	20.90/0.528/0.560	18.20/0.412/0.685
Isotropic TV-INR	32.20/0.895/0.205	29.30/0.825/0.278	26.50/0.742/0.360	24.10/0.650/0.445	21.50/0.535/0.565
Proposed DTV-INR	34.60 / 0.938 / 0.142	32.10 / 0.886 / 0.198	29.40 / 0.820 / 0.270	27.20 / 0.755 / 0.345	24.80 / 0.670 / 0.440

Table 2: Reconstruction robustness under increasing measurement noise

\sigma_{\eta}\in[0.01,0.10]

under

\times 4

super-resolution. Metrics reported: PSNR [dB] / SSIM / LPIPS (

\downarrow

Configuration	SIREN	Tikhonov	Isotropic	Anisotropic	Dynamic	PSNR [dB]
	Backbone	$L^{2}$ ( $\mu$ )	TV	$D(x)$	Tensor	/ SSIM
(1) Vanilla INR	✓	–	–	–	–	27.00 / 0.762
(2) Tikhonov Only	✓	✓	–	–	–	28.15 / 0.795
(3) Isotropic TV	✓	✓	✓	–	–	29.30 / 0.825
(4) Static Anisotropic $D(x)$	✓	✓	–	✓	–	31.42 / 0.856
(5) Complete DTV-INR	✓	✓	–	✓	✓	32.10 / 0.886

Table 3: Ablation study evaluating the functional components of the proposed DTV-INR formulation (

\times 4

super-resolution,

\sigma_{\eta}=0.03

Figure 1: Overall schematic of the Directional Total Variation-Regularized Implicit Neural Representation (DTV-INR) framework. The degraded observation $\mathbf{y}$ is transformed into an anisotropic diffusion tensor field $\mathbf{D}(\mathbf{x})$ that guides the coordinate-based implicit network $f_{\theta}$ to preserve structural boundaries and fine edges.

Figure 2: Quantitative comparison of PSNR across benchmark methods on medical and microstructure test datasets, highlighting the performance margins attained by DTV-INR.

Figure 3: Continuous super-resolution scaling evaluation. Reconstruction quality (PSNR) as a continuous function of magnification factor from $\times 2$ to $\times 8$ .

Figure 4: Robustness analysis against severe additive Gaussian and Rician noise profiles across varying signal-to-noise ratios (SNR).

Figure 5: Quantitative computational profiling: (a) Variational objective convergence over training iterations $k$ , demonstrating accelerated, monotonic descent and lower terminal energy for DTV-INR; (b) Robustness trajectory under severe observational noise $\sigma_{\eta}$ at $\times 4$ resolution; (c) Continuous scale generalization behavior across non-integer magnification factors $s\in[2.0,8.0]$ .

Figure 6: Qualitative super-resolution comparison ( $\times 4$ magnification with additive noise $\sigma_{\eta}=0.05$ ): (a) Ground Truth HR reference; (b) Degraded low-resolution observation; (c) Bicubic interpolation; (d) Vanilla unregularized SIREN; (e) Isotropic TV-INR showing characteristic blocky staircasing; (f) Proposed DTV-INR preserving sharp, smooth curvilinear edges without piecewise-constant segmentation artifacts.

Figure 7: Continuous super-resolution benchmark on the analytical Shepp–Logan phantom ( $4\times$ degradation factor, generated via main2.py ). Comparison highlights: (a) Bicubic baseline ( $17.52\,\mathrm{dB}$ , $\mathrm{SSIM}=0.584$ ) exhibiting severe blur; (b) Vanilla SIREN ( $18.15\,\mathrm{dB}$ , $\mathrm{SSIM}=0.612$ ) with high-frequency ringing; (c) SIREN + IsoTV ( $19.45\,\mathrm{dB}$ , $\mathrm{SSIM}=0.689$ ) afflicted by staircasing faceting; and (d) Proposed DTV-INR ( $20.61\,\mathrm{dB}$ , $\mathrm{SSIM}=0.748$ ) maintaining smooth curvilinear level sets and high geometric fidelity.

Figure 8: Magnified inspection of curvilinear boundary interfaces from the Shepp–Logan phantom reconstructions. While standard isotropic Total Variation induces false piecewise-planar faceting (staircasing) across continuous curves, the directional diffusion tensor in DTV-INR channels smoothing tangentially, thereby recovering pristine elliptical contours with intact boundary contrast.

Image Super-Resolution

Image super-resolution reconstructs high-resolution images from lower-resolution observations, balancing detail, fidelity, and computational cost.

See all 248 papers

Sep 1, 2026

Prior-Guided Implicit Neural Representations for Single-Subject Diffusion MRI Super-Resolution

Resolving complex fiber geometries in brain white matter requires high-resolution diffusion MRI at the cost of long acquisition times. This leads many clinical protocols to opt for low-resolution scans, making downstream microstructure estimation and tractography challenging. Implicit neural representations (INRs) can model the diffusion signal continuously, enabling native single-subject super-resolution by querying the network at arbitrary spatial coordinates, yet existing methods often suffer from long training times and lack a mechanism to incorporate anatomical priors to regularize super-resolution by constraining the space of plausible reconstructions. To address these limitations, we propose a novel transfer-learning framework that pre-trains an INR on a high-resolution template and then adapts it to subject-specific scans via registration and fine-tuning. For

4\times

through-plane super-resolution from 5 mm to 1.25 mm on Human Connectome Project (HCP) data, our method reduces NRMSE by 36-49% and increases FSIM by 24-43% over a recent baseline with

6\times

faster training, outperforming competing INR-based methods across both image quality and domain-specific metrics. Code is available on the project page at https://abdulkaderghandoura.github.io/research/msc-thesis/ .

Abdulkader Ghandoura, Marsil Zakour, William Consagra +1

Psychiatry Neuroimaging Laboratory Brigham and Women’s Hospital Harvard Medical School Boston, MA, USA · School of Computation, Information and Technology Technical University of Munich Munich, Germany · Department of Statistics University of South Carolina Columbia, SC, USA

Implicit Neural Representations Medical Image Super-Resolution Transfer Learning Diffusion MRI

Ask PDF

Jul 22, 2026

SIINR: Structurally Informed Implicit Neural Representations for super-resolution with uncertainty quantification of clinical quality diffusion MRI datasets

Diffusion Magnetic Resonance Imaging (dMRI) is a powerful tool for probing brain microstructure, but clinical acquisitions are often limited by low out-of-plane resolution, resulting in degraded structural information and reduced utility for advanced analysis. We introduce SIINR (Structurally Informed Implicit Neural Representations), a general framework for super-resoltion of clinical dMRI datasets while quantifying uncertainty in the reconstructed outputs. SIINR utilizes a supervised 3D U-net as a prior and combines it with a self-supervised implicit neural representation (INR) that fuses the high-resolution prior and the original low-resolution data. The INR enables joint modeling across spatial and angular domains, enforces data consistency, and provides analytic approximate posterior distributions for downstream uncertainty quantification. We validate the framework on a diverse set of open-access dMRI datasets, demonstrating that SIINR outperforms standard interpolation methods in both quantitative error metrics and qualitative anatomical fidelity. Experiments on clinical cases, including subjects with multiple sclerosis and brain lesions, illustrate the framework its ability to propagate intensity changes and flag uncertain regions in challenging scenarios. SIINR is flexible, modular, and can be adapted to different upsampling ratios and downstream tasks, providing a principled approach for enhancing clinical dMRI and supporting robust interpretation of derived neuroimaging metrics.

Tom Hendriks, William Consagra, Anna Vilanova +2

Department of Computer Science and Mathematics, Eindhoven University of Technology, Groene Loper 5, Eindhoven, 5612 AP, Noord-Brabant, The Netherlands. · Department of Statistics, University of South Carolina, Columbia, 29225, South Carolina, United States of America. · Psychiatry Neuroimaging Laboratory, Brigham and Women’s Hospital, Harvard Medical School, 399 Revolution Drive, Boston, 02215, MA, United States.

Implicit Neural Representations Uncertainty Quantification Medical Image Super-Resolution Magnetic Resonance Imaging Diffusion MRI Neuroimaging

Ask PDF

May 5, 2026

Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction

Implicit neural representations (INRs) have emerged as a powerful paradigm for medical imaging via physics-informed unsupervised learning. Classical INRs optimize an entire network from scratch for each subject, leading to inefficient training and suboptimal imaging quality. Recent initialization-based approaches attempt to inject population priors into pre-trained networks, yet they rely on high-quality images and often suffer from catastrophic forgetting during fine-tuning. We present DisINR, a novel INR framework that explicitly disentangles shared and subject-specific representations. DisINR introduces a shared encoder-decoder pair and subject-specific encoders, whose features are jointly decoded for image reconstruction. By integrating differentiable forward models, it pre-trains the shared modules directly from limited raw measurements, removing the need for pre-acquired high-quality images. During test-time adaptation, only the subject-specific encoder is optimized, while the shared pair remains frozen, effectively preserving learned priors. Extensive evaluations on three representative medical imaging tasks show that DisINR significantly outperforms state-of-the-art INRs in both reconstruction accuracy and efficiency.

Qing Wu, Xuanyu Tian, Chenhe Du +4

Medical AI Lab, Ant Group · ShanghaiTech University · Shanghai Jiao Tong University

Disentangled Representation Learning Implicit Neural Representations Image Reconstruction Medical Image Representation Learning

Ask PDF

Abstract

Image Super-Resolution

Explore similar work

Prior-Guided Implicit Neural Representations for Single-Subject Diffusion MRI Super-Resolution

SIINR: Structurally Informed Implicit Neural Representations for super-resolution with uncertainty quantification of clinical quality diffusion MRI datasets

Disentangled Learning Improves Implicit Neural Representations for Medical Reconstruction